A Human Behavior Recognition Method Based on Double-layer Conditional Random Field

Abstract

The invention discloses a human body behavior recognition method based on a double-layer conditional random field, which belongs to the field of computer vision behavior recognition. Firstly, the human body posture of the action subject in the RGB-D video and the information features of the objects that may interact with it are extracted respectively, and the score information of each small video obtained by the interactive objects after the RGB-D video segmentation is calculated as the global feature. Then, the top-level conditional random field is modeled to capture the high-order correlation between human behaviors, the bottom-level conditional random field is modeled to enrich the underlying structure of human behavior, and finally a discriminant classification model of two-layer conditional random field is constructed. Next, exact inference and a structured support vector machine classifier are used to learn the discriminative classification model parameters for a two-layer conditional random field. Finally, predict the human behavior category in the test video according to the learned model parameters and the obtained model. The invention improves the recognition accuracy of human behaviors to a certain extent.

Description

technical field [0001] The invention relates to the technical field of computer vision action recognition, in particular to a human action recognition method based on double-layer conditional random fields (Double-layer conditional random fields model for human action recognition, DL-CRFs). Background technique [0002] Human behavior recognition in video sequences is a research topic involving computer vision, pattern recognition and artificial intelligence. It has been a hot research topic because of its wide application value in business, medical and sports fields. [0003] Literature [Koppula H S, Gupta R, Saxena A. Learning Human Activities and Object Affordances from RGB-D Videos [J]. International Journal of Robotics Research, 2013, 32 (8): 951-970.] according to the complexity of human behavior Behaviors are divided into high-level activities and simple actions. Simple behavior refers to an indivisible behavior with at most one interactive object in the process, and...

AI Technical Summary

Problems solved by technology

The obvious shortcoming of the generative model is that when there are complex correlations between the input sample data, the modeling of the joint distribution will become complicated or even inaccurate

However, the above-mentioned existing behavior recognition methods based on probabilistic graphical models have not considered both the internal potential structure of the human behavior state and the high-order correlation between human behavior states, and there is still the problem of low recognition accuracy.

Images